Dataset Information

Optimizing the Experimental Method for Stomata-Profiling Automation of Soybean Leaves Based on Deep Learning.

ABSTRACT: Stomatal observation and automatic stomatal detection are useful analyses of stomata for taxonomic, biological, physiological, and eco-physiological studies. We present a new clearing method for improved microscopic imaging of stomata in soybean followed by automated stomatal detection by deep learning. We tested eight clearing agent formulations based upon different ethanol and sodium hypochlorite (NaOCl) concentrations in order to improve the transparency in leaves. An optimal formulation-a 1:1 (v/v) mixture of 95% ethanol and NaOCl (6-14%)-produced better quality images of soybean stomata. Additionally, we evaluated fixatives and dehydrating agents and selected absolute ethanol for both fixation and dehydration. This is a good substitute for formaldehyde, which is more toxic to handle. Using imaging data from this clearing method, we developed an automatic stomatal detector using deep learning and improved a deep-learning algorithm that automatically analyzes stomata through an object detection model using YOLO. The YOLO deep-learning model successfully recognized stomata with high mAP (~0.99). A web-based interface is provided to apply the model of stomatal detection for any soybean data that makes use of the new clearing protocol.

SUBMITTER: Sultana SN

PROVIDER: S-EPMC8708663 | biostudies-literature | 2021 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Optimizing the Experimental Method for Stomata-Profiling Automation of Soybean Leaves Based on Deep Learning.

Sultana Syada Nizer SN Park Halim H Choi Sung Hoon SH Jo Hyun H Song Jong Tae JT Lee Jeong-Dong JD Kang Yang Jae YJ

Plants (Basel, Switzerland) 20211210 12

Stomatal observation and automatic stomatal detection are useful analyses of stomata for taxonomic, biological, physiological, and eco-physiological studies. We present a new clearing method for improved microscopic imaging of stomata in soybean followed by automated stomatal detection by deep learning. We tested eight clearing agent formulations based upon different ethanol and sodium hypochlorite (NaOCl) concentrations in order to improve the transparency in leaves. An optimal formulation-a 1: ...[more]

PMID: 34961184

Similar Datasets

Project description:BackgroundImmediately following germination, the developing soybean seedling relies on the nutrient reserves stored in the cotyledons to sustain heterotrophic growth. During the seed filling period, developing seeds rely on the transport of nutrients from the trifoliate leaves. In soybean, both cotyledons and leaves develop the capacity for photosynthesis, and subsequently senesce and abscise once their function has ended. Before this occurs, the nutrients they contain are mobilized and transported to other parts of the plant. These processes are carefully orchestrated by genetic regulation throughout the development of the leaf or cotyledon.ResultsTo identify genes involved in the processes of leaf or cotyledon development and senescence in soybean, we used RNA-seq to profile multiple stages of cotyledon and leaf tissues. Differentially expressed genes between stages of leaf or cotyledon development were determined, major patterns of gene expression were defined, and shared genes were identified. Over 38,000 transcripts were expressed during the course of leaf and cotyledon development. Of those transcripts, 5,000 were expressed in a tissue specific pattern. Of the genes that were differentially expressed between both later stage tissues, 90 % had the same direction of change, suggesting that the mechanisms of senescence are conserved between tissues. Analysis of the enrichment of biological functions within genes sharing common expression profiles highlights the main processes occurring within these defined temporal windows of leaf and cotyledon development. Over 1,000 genes were identified with predicted regulatory functions that may have a role in control of leaf or cotyledon senescence.ConclusionsThe process of leaf and cotyledon development can be divided into distinct stages characterized by the expression of specific gene sets. The importance of the WRKY, NAC, and GRAS family transcription factors as major regulators of plant senescence is confirmed for both soybean leaf and cotyledon tissues. These results help validate functional annotation for soybean genes and promoters.

Project description:BackgroundDespite the potential of the endoplasmic reticulum (ER) stress response to accommodate adaptive pathways, its integration with other environmental-induced responses is poorly understood in plants. We have previously demonstrated that the ER-stress sensor binding protein (BiP) from soybean exhibits an unusual response to drought. The members of the soybean BiP gene family are differentially regulated by osmotic stress and soybean BiP confers tolerance to drought. While these results may reflect crosstalk between the osmotic and ER-stress signaling pathways, the lack of mutants, transcriptional response profiles to stresses and genome sequence information of this relevant crop has limited our attempts to identify integrated networks between osmotic and ER stress-induced adaptive responses. As a fundamental step towards this goal, we performed global expression profiling on soybean leaves exposed to polyethylene glycol treatment (osmotic stress) or to ER stress inducers.ResultsThe up-regulated stress-specific changes unmasked the major branches of the ER-stress response, which include enhancing protein folding and degradation in the ER, as well as specific osmotically regulated changes linked to cellular responses induced by dehydration. However, a small proportion (5.5%) of total up-regulated genes represented a shared response that seemed to integrate the two signaling pathways. These co-regulated genes were considered downstream targets based on similar induction kinetics and a synergistic response to the combination of osmotic- and ER-stress-inducing treatments. Genes in this integrated pathway with the strongest synergistic induction encoded proteins with diverse roles, such as plant-specific development and cell death (DCD) domain-containing proteins, an ubiquitin-associated (UBA) protein homolog and NAC domain-containing proteins. This integrated pathway diverged further from characterized specific branches of ER-stress as downstream targets were inversely regulated by osmotic stress.ConclusionThe present ER-stress- and osmotic-stress-induced transcriptional studies demonstrate a clear predominance of stimulus-specific positive changes over shared responses on soybean leaves. This scenario indicates that polyethylene glycol (PEG)-induced cellular dehydration and ER stress elicited very different up-regulated responses within a 10-h stress treatment regime. In addition to identifying ER-stress and osmotic-stress-specific responses in soybean (Glycine max), our global expression-profiling analyses provided a list of candidate regulatory components, which may integrate the osmotic-stress and ER-stress signaling pathways in plants.

Dataset Information

Optimizing the Experimental Method for Stomata-Profiling Automation of Soybean Leaves Based on Deep Learning.

Publications

Optimizing the Experimental Method for Stomata-Profiling Automation of Soybean Leaves Based on Deep Learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets